The patch titled
Subject: mm/mempolicy: introduce MPOL_WEIGHTED_INTERLEAVE for weighted interleaving
has been added to the -mm mm-unstable branch. Its filename is
mm-mempolicy-introduce-mpol_weighted_interleave-for-weighted-interleaving.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-mempolicy-introduce-mpol_weighted_interleave-for-weighted-interleaving.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Gregory Price <gourry.memverge@xxxxxxxxx>
Subject: mm/mempolicy: introduce MPOL_WEIGHTED_INTERLEAVE for weighted interleaving
Date: Thu, 25 Jan 2024 13:43:44 -0500
When a system has multiple NUMA nodes and it becomes bandwidth hungry,
using the current MPOL_INTERLEAVE could be an wise option.
However, if those NUMA nodes consist of different types of memory such
as socket-attached DRAM and CXL/PCIe attached DRAM, the round-robin
based interleave policy does not optimally distribute data to make use
of their different bandwidth characteristics.
Instead, interleave is more effective when the allocation policy follows
each NUMA nodes' bandwidth weight rather than a simple 1:1 distribution.
This patch introduces a new memory policy, MPOL_WEIGHTED_INTERLEAVE,
enabling weighted interleave between NUMA nodes. Weighted interleave
allows for proportional distribution of memory across multiple numa
nodes, preferably apportioned to match the bandwidth of each node.
For example, if a system has 1 CPU node (0), and 2 memory nodes (0,1),
with bandwidth of (100GB/s, 50GB/s) respectively, the appropriate
weight distribution is (2:1).
Weights for each node can be assigned via the new sysfs extension:
/sys/kernel/mm/mempolicy/weighted_interleave/
For now, the default value of all nodes will be `1`, which matches
the behavior of standard 1:1 round-robin interleave. An extension
will be added in the future to allow default values to be registered
at kernel and device bringup time.
The policy allocates a number of pages equal to the set weights. For
example, if the weights are (2,1), then 2 pages will be allocated on
node0 for every 1 page allocated on node1.
The new flag MPOL_WEIGHTED_INTERLEAVE can be used in set_mempolicy(2)
and mbind(2).
There are 3 integration points:
weighted_interleave_nodes:
Counts the number of allocations as they occur, and applies the
weight for the current node. When the weight reaches 0, switch
to the next node.
weighted_interleave_nid:
Gets the total weight of the nodemask as well as each individual
node weight, then calculates the node based on the given index.
bulk_array_weighted_interleave:
Gets the total weight of the nodemask as well as each individual
node weight, then calculates the number of "interleave rounds" as
well as any delta ("partial round"). Calculates the number of
pages for each node and allocates them.
If a node was scheduled for interleave via interleave_nodes, the
current weight (pol->cur_il_weight) will be allocated first, before
the remaining bulk calculation is done.
One piece of complexity is the interaction between a recent refactor
which split the logic to acquire the "ilx" (interleave index) of an
allocation and the actually application of the interleave. The
calculation of the `interleave index` is done by `get_vma_policy()`,
while the actual selection of the node will be later appliex by the
relevant weighted_interleave function.
Link: https://lkml.kernel.org/r/20240125184345.47074-4-gregory.price@xxxxxxxxxxxx
Suggested-by: Hasan Al Maruf <Hasan.Maruf@xxxxxxx>
Signed-off-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
Co-developed-by: Rakie Kim <rakie.kim@xxxxxx>
Signed-off-by: Rakie Kim <rakie.kim@xxxxxx>
Co-developed-by: Honggyu Kim <honggyu.kim@xxxxxx>
Signed-off-by: Honggyu Kim <honggyu.kim@xxxxxx>
Co-developed-by: Hyeongtak Ji <hyeongtak.ji@xxxxxx>
Signed-off-by: Hyeongtak Ji <hyeongtak.ji@xxxxxx>
Co-developed-by: Srinivasulu Thanneeru <sthanneeru.opensrc@xxxxxxxxxx>
Signed-off-by: Srinivasulu Thanneeru <sthanneeru.opensrc@xxxxxxxxxx>
Co-developed-by: Ravi Jonnalagadda <ravis.opensrc@xxxxxxxxxx>
Signed-off-by: Ravi Jonnalagadda <ravis.opensrc@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Frank van der Linden <fvdl@xxxxxxxxxx>
Cc: Huang Ying <ying.huang@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/admin-guide/mm/numa_memory_policy.rst | 9
include/linux/mempolicy.h | 3
include/uapi/linux/mempolicy.h | 1
mm/mempolicy.c | 274 +++++++++-
4 files changed, 283 insertions(+), 4 deletions(-)
--- a/Documentation/admin-guide/mm/numa_memory_policy.rst~mm-mempolicy-introduce-mpol_weighted_interleave-for-weighted-interleaving
+++ a/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -250,6 +250,15 @@ MPOL_PREFERRED_MANY
can fall back to all existing numa nodes. This is effectively
MPOL_PREFERRED allowed for a mask rather than a single node.
+MPOL_WEIGHTED_INTERLEAVE
+ This mode operates the same as MPOL_INTERLEAVE, except that
+ interleaving behavior is executed based on weights set in
+ /sys/kernel/mm/mempolicy/weighted_interleave/
+
+ Weighted interleave allocates pages on nodes according to a
+ weight. For example if nodes [0,1] are weighted [5,2], 5 pages
+ will be allocated on node0 for every 2 pages allocated on node1.
+
NUMA memory policy supports the following optional mode flags:
MPOL_F_STATIC_NODES
--- a/include/linux/mempolicy.h~mm-mempolicy-introduce-mpol_weighted_interleave-for-weighted-interleaving
+++ a/include/linux/mempolicy.h
@@ -54,6 +54,9 @@ struct mempolicy {
nodemask_t cpuset_mems_allowed; /* relative to these nodes */
nodemask_t user_nodemask; /* nodemask passed by user */
} w;
+
+ /* Weighted interleave settings */
+ u8 cur_il_weight;
};
/*
--- a/include/uapi/linux/mempolicy.h~mm-mempolicy-introduce-mpol_weighted_interleave-for-weighted-interleaving
+++ a/include/uapi/linux/mempolicy.h
@@ -23,6 +23,7 @@ enum {
MPOL_INTERLEAVE,
MPOL_LOCAL,
MPOL_PREFERRED_MANY,
+ MPOL_WEIGHTED_INTERLEAVE,
MPOL_MAX, /* always last member of enum */
};
--- a/mm/mempolicy.c~mm-mempolicy-introduce-mpol_weighted_interleave-for-weighted-interleaving
+++ a/mm/mempolicy.c
@@ -19,6 +19,13 @@
* for anonymous memory. For process policy an process counter
* is used.
*
+ * weighted interleave
+ * Allocate memory interleaved over a set of nodes based on
+ * a set of weights (per-node), with normal fallback if it
+ * fails. Otherwise operates the same as interleave.
+ * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated
+ * on node 0 for every 1 page allocated on node 1.
+ *
* bind Only allocate memory on a specific set of nodes,
* no fallback.
* FIXME: memory is allocated starting with the first node
@@ -314,6 +321,7 @@ static struct mempolicy *mpol_new(unsign
policy->mode = mode;
policy->flags = flags;
policy->home_node = NUMA_NO_NODE;
+ policy->cur_il_weight = 0;
return policy;
}
@@ -426,6 +434,10 @@ static const struct mempolicy_operations
.create = mpol_new_nodemask,
.rebind = mpol_rebind_preferred,
},
+ [MPOL_WEIGHTED_INTERLEAVE] = {
+ .create = mpol_new_nodemask,
+ .rebind = mpol_rebind_nodemask,
+ },
};
static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist,
@@ -843,7 +855,8 @@ static long do_set_mempolicy(unsigned sh
old = current->mempolicy;
current->mempolicy = new;
- if (new && new->mode == MPOL_INTERLEAVE)
+ if (new && (new->mode == MPOL_INTERLEAVE ||
+ new->mode == MPOL_WEIGHTED_INTERLEAVE))
current->il_prev = MAX_NUMNODES-1;
task_unlock(current);
mpol_put(old);
@@ -869,6 +882,7 @@ static void get_policy_nodemask(struct m
case MPOL_INTERLEAVE:
case MPOL_PREFERRED:
case MPOL_PREFERRED_MANY:
+ case MPOL_WEIGHTED_INTERLEAVE:
*nodes = pol->nodes;
break;
case MPOL_LOCAL:
@@ -953,6 +967,13 @@ static long do_get_mempolicy(int *policy
} else if (pol == current->mempolicy &&
pol->mode == MPOL_INTERLEAVE) {
*policy = next_node_in(current->il_prev, pol->nodes);
+ } else if (pol == current->mempolicy &&
+ (pol->mode == MPOL_WEIGHTED_INTERLEAVE)) {
+ if (pol->cur_il_weight)
+ *policy = current->il_prev;
+ else
+ *policy = next_node_in(current->il_prev,
+ pol->nodes);
} else {
err = -EINVAL;
goto out;
@@ -1765,7 +1786,8 @@ struct mempolicy *__get_vma_policy(struc
* @vma: virtual memory area whose policy is sought
* @addr: address in @vma for shared policy lookup
* @order: 0, or appropriate huge_page_order for interleaving
- * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE
+ * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or
+ * MPOL_WEIGHTED_INTERLEAVE
*
* Returns effective policy for a VMA at specified address.
* Falls back to current->mempolicy or system default policy, as necessary.
@@ -1782,7 +1804,8 @@ struct mempolicy *get_vma_policy(struct
pol = __get_vma_policy(vma, addr, ilx);
if (!pol)
pol = get_task_policy(current);
- if (pol->mode == MPOL_INTERLEAVE) {
+ if (pol->mode == MPOL_INTERLEAVE ||
+ pol->mode == MPOL_WEIGHTED_INTERLEAVE) {
*ilx += vma->vm_pgoff >> order;
*ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order);
}
@@ -1832,6 +1855,44 @@ bool apply_policy_zone(struct mempolicy
return zone >= dynamic_policy_zone;
}
+static unsigned int weighted_interleave_nodes(struct mempolicy *policy)
+{
+ unsigned int node, next;
+ struct task_struct *me = current;
+ u8 __rcu *table;
+ u8 weight;
+
+ node = next_node_in(me->il_prev, policy->nodes);
+ if (node == MAX_NUMNODES)
+ return node;
+
+ /* on first alloc after setting mempolicy, acquire first weight */
+ if (unlikely(!policy->cur_il_weight)) {
+ rcu_read_lock();
+ table = rcu_dereference(iw_table);
+ /* detect system-default values */
+ weight = table ? table[node] : 1;
+ policy->cur_il_weight = weight ? weight : 1;
+ rcu_read_unlock();
+ }
+
+ /* account for this allocation call */
+ policy->cur_il_weight--;
+
+ /* if now at 0, move to next node and set up that node's weight */
+ if (unlikely(!policy->cur_il_weight)) {
+ me->il_prev = node;
+ next = next_node_in(node, policy->nodes);
+ rcu_read_lock();
+ table = rcu_dereference(iw_table);
+ /* detect system-default values */
+ weight = table ? table[next] : 1;
+ policy->cur_il_weight = weight ? weight : 1;
+ rcu_read_unlock();
+ }
+ return node;
+}
+
/* Do dynamic interleaving for a process */
static unsigned int interleave_nodes(struct mempolicy *policy)
{
@@ -1866,6 +1927,9 @@ unsigned int mempolicy_slab_node(void)
case MPOL_INTERLEAVE:
return interleave_nodes(policy);
+ case MPOL_WEIGHTED_INTERLEAVE:
+ return weighted_interleave_nodes(policy);
+
case MPOL_BIND:
case MPOL_PREFERRED_MANY:
{
@@ -1904,6 +1968,39 @@ static unsigned int read_once_policy_nod
return nodes_weight(*mask);
}
+static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx)
+{
+ nodemask_t nodemask;
+ unsigned int target, nr_nodes;
+ u8 __rcu *table;
+ unsigned int weight_total = 0;
+ u8 weight;
+ int nid;
+
+ nr_nodes = read_once_policy_nodemask(pol, &nodemask);
+ if (!nr_nodes)
+ return numa_node_id();
+
+ rcu_read_lock();
+ table = rcu_dereference(iw_table);
+ /* calculate the total weight */
+ for_each_node_mask(nid, nodemask)
+ weight_total += table ? table[nid] : 1;
+
+ /* Calculate the node offset based on totals */
+ target = ilx % weight_total;
+ nid = first_node(nodemask);
+ while (target) {
+ weight = table ? table[nid] : 1;
+ if (target < weight)
+ break;
+ target -= weight;
+ nid = next_node_in(nid, nodemask);
+ }
+ rcu_read_unlock();
+ return nid;
+}
+
/*
* Do static interleaving for interleave index @ilx. Returns the ilx'th
* node in pol->nodes (starting from ilx=0), wrapping around if ilx
@@ -1964,6 +2061,11 @@ static nodemask_t *policy_nodemask(gfp_t
*nid = (ilx == NO_INTERLEAVE_INDEX) ?
interleave_nodes(pol) : interleave_nid(pol, ilx);
break;
+ case MPOL_WEIGHTED_INTERLEAVE:
+ *nid = (ilx == NO_INTERLEAVE_INDEX) ?
+ weighted_interleave_nodes(pol) :
+ weighted_interleave_nid(pol, ilx);
+ break;
}
return nodemask;
@@ -2025,6 +2127,7 @@ bool init_nodemask_of_mempolicy(nodemask
case MPOL_PREFERRED_MANY:
case MPOL_BIND:
case MPOL_INTERLEAVE:
+ case MPOL_WEIGHTED_INTERLEAVE:
*mask = mempolicy->nodes;
break;
@@ -2124,7 +2227,8 @@ struct page *alloc_pages_mpol(gfp_t gfp,
* If the policy is interleave or does not allow the current
* node in its nodemask, we allocate the standard way.
*/
- if (pol->mode != MPOL_INTERLEAVE &&
+ if ((pol->mode != MPOL_INTERLEAVE &&
+ pol->mode != MPOL_WEIGHTED_INTERLEAVE) &&
(!nodemask || node_isset(nid, *nodemask))) {
/*
* First, try to allocate THP only on local node, but
@@ -2260,6 +2364,156 @@ static unsigned long alloc_pages_bulk_ar
return total_allocated;
}
+static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp,
+ struct mempolicy *pol, unsigned long nr_pages,
+ struct page **page_array)
+{
+ struct task_struct *me = current;
+ unsigned long total_allocated = 0;
+ unsigned long nr_allocated;
+ unsigned long rounds;
+ unsigned long node_pages, delta;
+ u8 weight, resume_weight;
+ u8 __rcu *table;
+ u8 *weights;
+ unsigned int weight_total = 0;
+ unsigned long rem_pages = nr_pages;
+ nodemask_t nodes;
+ int nnodes, node, resume_node, next_node;
+ int prev_node = me->il_prev;
+ int i;
+
+ if (!nr_pages)
+ return 0;
+
+ nnodes = read_once_policy_nodemask(pol, &nodes);
+ if (!nnodes)
+ return 0;
+
+ /* Continue allocating from most recent node and adjust the nr_pages */
+ if (pol->cur_il_weight) {
+ node = next_node_in(prev_node, nodes);
+ node_pages = pol->cur_il_weight;
+ if (node_pages > rem_pages)
+ node_pages = rem_pages;
+ nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages,
+ NULL, page_array);
+ page_array += nr_allocated;
+ total_allocated += nr_allocated;
+ /*
+ * if that's all the pages, no need to interleave, otherwise
+ * we need to set up the next interleave node/weight correctly.
+ */
+ if (rem_pages < pol->cur_il_weight) {
+ /* stay on current node, adjust cur_il_weight */
+ pol->cur_il_weight -= rem_pages;
+ return total_allocated;
+ } else if (rem_pages == pol->cur_il_weight) {
+ /* move to next node / weight */
+ me->il_prev = node;
+ next_node = next_node_in(node, nodes);
+ rcu_read_lock();
+ table = rcu_dereference(iw_table);
+ weight = table ? table[next_node] : 1;
+ /* detect system-default usage */
+ pol->cur_il_weight = weight ? weight : 1;
+ rcu_read_unlock();
+ return total_allocated;
+ }
+ /* Otherwise we adjust nr_pages down, and continue from there */
+ rem_pages -= pol->cur_il_weight;
+ pol->cur_il_weight = 0;
+ prev_node = node;
+ }
+
+ /* create a local copy of node weights to operate on outside rcu */
+ weights = kmalloc(nr_node_ids, GFP_KERNEL);
+ if (!weights)
+ return total_allocated;
+
+ rcu_read_lock();
+ table = rcu_dereference(iw_table);
+ /* If table is not registered, use system defaults */
+ if (table)
+ memcpy(weights, iw_table, nr_node_ids);
+ else
+ memset(weights, 1, nr_node_ids);
+ rcu_read_unlock();
+
+ /* calculate total, detect system default usage */
+ for_each_node_mask(node, nodes) {
+ /* detect system-default usage */
+ if (!weights[node])
+ weights[node] = 1;
+ weight_total += weights[node];
+ }
+
+ /*
+ * Now we can continue allocating from 0 instead of an offset
+ * We calculate the number of rounds and any partial rounds so
+ * that we minimize the number of calls to __alloc_pages_bulk
+ * This requires us to track which node we should resume from.
+ *
+ * if (rounds > 0) and (delta == 0), resume_node will always be
+ * the current value of prev_node, which may be NUMA_NO_NODE if
+ * this is the first allocation after a policy is replaced. The
+ * resume weight will be the weight of the next node.
+ *
+ * if (delta > 0) and delta is depleted exactly on a node-weight
+ * boundary, resume node will be the node last allocated from when
+ * delta reached 0.
+ *
+ * if (delta > 0) and delta is not depleted on a node-weight boundary,
+ * resume node will be the node prior to the node last allocated from.
+ *
+ * (rounds == 0) and (delta == 0) is not possible (earlier exit)
+ */
+ rounds = rem_pages / weight_total;
+ delta = rem_pages % weight_total;
+ resume_node = prev_node;
+ resume_weight = weights[next_node_in(prev_node, nodes)];
+ /* If no delta, we'll resume from current prev_node and first weight */
+ for (i = 0; i < nnodes; i++) {
+ node = next_node_in(prev_node, nodes);
+ weight = weights[node];
+ node_pages = weight * rounds;
+ /* If a delta exists, add this node's portion of the delta */
+ if (delta > weight) {
+ node_pages += weight;
+ delta -= weight;
+ resume_node = node;
+ } else if (delta) {
+ node_pages += delta;
+ if (delta == weight) {
+ /* resume from next node with its weight */
+ resume_node = node;
+ next_node = next_node_in(node, nodes);
+ resume_weight = weights[next_node];
+ } else {
+ /* resume from this node w/ remaining weight */
+ resume_node = prev_node;
+ resume_weight = weight - (node_pages % weight);
+ }
+ delta = 0;
+ }
+ /* node_pages can be 0 if an allocation fails and rounds == 0 */
+ if (!node_pages)
+ break;
+ nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages,
+ NULL, page_array);
+ page_array += nr_allocated;
+ total_allocated += nr_allocated;
+ if (total_allocated == nr_pages)
+ break;
+ prev_node = node;
+ }
+ /* resume allocating from the calculated node and weight */
+ me->il_prev = resume_node;
+ pol->cur_il_weight = resume_weight;
+ kfree(weights);
+ return total_allocated;
+}
+
static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
struct mempolicy *pol, unsigned long nr_pages,
struct page **page_array)
@@ -2300,6 +2554,10 @@ unsigned long alloc_pages_bulk_array_mem
return alloc_pages_bulk_array_interleave(gfp, pol,
nr_pages, page_array);
+ if (pol->mode == MPOL_WEIGHTED_INTERLEAVE)
+ return alloc_pages_bulk_array_weighted_interleave(
+ gfp, pol, nr_pages, page_array);
+
if (pol->mode == MPOL_PREFERRED_MANY)
return alloc_pages_bulk_array_preferred_many(gfp,
numa_node_id(), pol, nr_pages, page_array);
@@ -2375,6 +2633,7 @@ bool __mpol_equal(struct mempolicy *a, s
case MPOL_INTERLEAVE:
case MPOL_PREFERRED:
case MPOL_PREFERRED_MANY:
+ case MPOL_WEIGHTED_INTERLEAVE:
return !!nodes_equal(a->nodes, b->nodes);
case MPOL_LOCAL:
return true;
@@ -2511,6 +2770,10 @@ int mpol_misplaced(struct folio *folio,
polnid = interleave_nid(pol, ilx);
break;
+ case MPOL_WEIGHTED_INTERLEAVE:
+ polnid = weighted_interleave_nid(pol, ilx);
+ break;
+
case MPOL_PREFERRED:
if (node_isset(curnid, pol->nodes))
goto out;
@@ -2885,6 +3148,7 @@ static const char * const policy_modes[]
[MPOL_PREFERRED] = "prefer",
[MPOL_BIND] = "bind",
[MPOL_INTERLEAVE] = "interleave",
+ [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave",
[MPOL_LOCAL] = "local",
[MPOL_PREFERRED_MANY] = "prefer (many)",
};
@@ -2944,6 +3208,7 @@ int mpol_parse_str(char *str, struct mem
}
break;
case MPOL_INTERLEAVE:
+ case MPOL_WEIGHTED_INTERLEAVE:
/*
* Default to online nodes with memory if no nodelist
*/
@@ -3054,6 +3319,7 @@ void mpol_to_str(char *buffer, int maxle
case MPOL_PREFERRED_MANY:
case MPOL_BIND:
case MPOL_INTERLEAVE:
+ case MPOL_WEIGHTED_INTERLEAVE:
nodes = pol->nodes;
break;
default:
_
Patches currently in -mm which might be from gourry.memverge@xxxxxxxxx are
mm-mempolicy-refactor-a-read-once-mechanism-into-a-function-for-re-use.patch
mm-mempolicy-introduce-mpol_weighted_interleave-for-weighted-interleaving.patch
mm-mempolicy-change-cur_il_weight-to-atomic-and-carry-the-node-with-it.patch
